The problematics of creation and development of bank erosion, follow-up repairs of abrasion damaged banks and development of abrasion progress prognostic methods is often discussed. One of the contributions to this discussion is presentation of ''Modificated Methods of Abrasion Terminal Line Determination''. The prognosis of bank erosion advance is determined also in areas, where original condition of bank is unknown. This method was successfully verified during years 1998-2001 at Brno Reservoir on the Svratka River and can be used at other dam reservoirs as well. and O problematice vzniku a rozvoje břehové abraze, o návrzích následné sanace abrazí poškozených břehů a vývoji prognostických metod postupu abraze se v posledních letech diskutuje stále častěji. Jedním z příspěvků k této diskusi je i prezentace ''modifikované metody určení abrazní terminanty''. Jedná se zde o stanovení prognózy postupu břehové abraze, a to i v oblastech, ve kterých neznáme původní stav pobřeží. Tato metoda byla úspěšně ověřována v letech 1998-2001 na údolní nádrži Brno na řece Svratce a je široce použitelná i na jiných vodních dílech.
Prediction of reservoir level fluctuation is important in the operation, design, and security of dams. In this paper, Artificial Neural Networks (ANN) is used for modeling. In such modeling approaches, it is possible to determine dam reservoir level and water balance (budget) by taking the monthly average precipitation and needed parameters into consideration. The basic data are available for over 29 years at the Tahtakőprű Dam in the southeast Mediterranean region of Turkey. As a sub-approach of ANN, a multi layer perceptron (MLP) is used. Bayesian regularization back-propagation training algorithm is employed for optimization of the network. MLP results are compared with the results of conventional multiple linear regression (MLR) and autoregressive (AR) models. The comparison shows that the ANN model provides better performance than the mentioned models in reservoir level estimation.